What Are You Doing? Effects of Intermediate Feedback from Agentic LLM In-Car Assistants During Multi-Step Processing

TL;DR

This study examines how intermediate feedback from agentic LLM-based in-car assistants affects user experience, trust, and perceived speed during multi-step tasks, revealing benefits of adaptive communication strategies.

Contribution

It provides empirical evidence on the impact of feedback timing and verbosity, and offers design guidelines for improving agentic assistant interactions in driving contexts.

Findings

Intermediate feedback improves perceived speed and trust.

Users prefer adaptive transparency based on context.

Feedback reduces task load across complexities.

Abstract

Agentic AI assistants that autonomously perform multi-step tasks raise open questions for user experience: how should such systems communicate progress and reasoning during extended operations, especially in attention-critical contexts such as driving? We investigate feedback timing and verbosity from agentic LLM-based in-car assistants through a controlled, mixed-methods study (N=45) comparing planned steps and intermediate results feedback against silent operation with final-only response. Using a dual-task paradigm with an in-car voice assistant, we found that intermediate feedback significantly improved perceived speed, trust, and user experience while reducing task load - effects that held across varying task complexities and interaction contexts. Interviews further revealed user preferences for an adaptive approach: high initial transparency to establish trust, followed by progressively reducing verbosity as systems prove reliable, with adjustments based on task stakes and situational context. We translate our empirical findings into design implications for feedback timing and verbosity in agentic assistants, balancing transparency and efficiency.